forked from huggingface/diffusers
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathhub_utils.py
More file actions
562 lines (501 loc) 路 23.4 KB
/
Copy pathhub_utils.py
File metadata and controls
562 lines (501 loc) 路 23.4 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
# coding=utf-8
# Copyright 2025 The HuggingFace Inc. team.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import json
import os
import re
import sys
import tempfile
import warnings
from pathlib import Path
from typing import Dict, List, Optional, Union
from uuid import uuid4
from huggingface_hub import (
DDUFEntry,
ModelCard,
ModelCardData,
create_repo,
hf_hub_download,
model_info,
snapshot_download,
upload_folder,
)
from huggingface_hub.constants import HF_HUB_DISABLE_TELEMETRY, HF_HUB_OFFLINE
from huggingface_hub.file_download import REGEX_COMMIT_HASH
from huggingface_hub.utils import (
EntryNotFoundError,
RepositoryNotFoundError,
RevisionNotFoundError,
is_jinja_available,
validate_hf_hub_args,
)
from packaging import version
from requests import HTTPError
from .. import __version__
from .constants import (
DEPRECATED_REVISION_ARGS,
HUGGINGFACE_CO_RESOLVE_ENDPOINT,
SAFETENSORS_WEIGHTS_NAME,
WEIGHTS_NAME,
)
from .import_utils import (
ENV_VARS_TRUE_VALUES,
_flax_version,
_jax_version,
_onnxruntime_version,
_torch_version,
is_flax_available,
is_onnx_available,
is_torch_available,
)
from .logging import get_logger
logger = get_logger(__name__)
MODEL_CARD_TEMPLATE_PATH = Path(__file__).parent / "model_card_template.md"
SESSION_ID = uuid4().hex
def http_user_agent(user_agent: Union[Dict, str, None] = None) -> str:
"""
Formats a user-agent string with basic info about a request.
"""
ua = f"diffusers/{__version__}; python/{sys.version.split()[0]}; session_id/{SESSION_ID}"
if HF_HUB_DISABLE_TELEMETRY or HF_HUB_OFFLINE:
return ua + "; telemetry/off"
if is_torch_available():
ua += f"; torch/{_torch_version}"
if is_flax_available():
ua += f"; jax/{_jax_version}"
ua += f"; flax/{_flax_version}"
if is_onnx_available():
ua += f"; onnxruntime/{_onnxruntime_version}"
# CI will set this value to True
if os.environ.get("DIFFUSERS_IS_CI", "").upper() in ENV_VARS_TRUE_VALUES:
ua += "; is_ci/true"
if isinstance(user_agent, dict):
ua += "; " + "; ".join(f"{k}/{v}" for k, v in user_agent.items())
elif isinstance(user_agent, str):
ua += "; " + user_agent
return ua
def load_or_create_model_card(
repo_id_or_path: str = None,
token: Optional[str] = None,
is_pipeline: bool = False,
from_training: bool = False,
model_description: Optional[str] = None,
base_model: str = None,
prompt: Optional[str] = None,
license: Optional[str] = None,
widget: Optional[List[dict]] = None,
inference: Optional[bool] = None,
) -> ModelCard:
"""
Loads or creates a model card.
Args:
repo_id_or_path (`str`):
The repo id (e.g., "runwayml/stable-diffusion-v1-5") or local path where to look for the model card.
token (`str`, *optional*):
Authentication token. Will default to the stored token. See https://huggingface.co/settings/token for more
details.
is_pipeline (`bool`):
Boolean to indicate if we're adding tag to a [`DiffusionPipeline`].
from_training: (`bool`): Boolean flag to denote if the model card is being created from a training script.
model_description (`str`, *optional*): Model description to add to the model card. Helpful when using
`load_or_create_model_card` from a training script.
base_model (`str`): Base model identifier (e.g., "stabilityai/stable-diffusion-xl-base-1.0"). Useful
for DreamBooth-like training.
prompt (`str`, *optional*): Prompt used for training. Useful for DreamBooth-like training.
license: (`str`, *optional*): License of the output artifact. Helpful when using
`load_or_create_model_card` from a training script.
widget (`List[dict]`, *optional*): Widget to accompany a gallery template.
inference: (`bool`, optional): Whether to turn on inference widget. Helpful when using
`load_or_create_model_card` from a training script.
"""
if not is_jinja_available():
raise ValueError(
"Modelcard rendering is based on Jinja templates."
" Please make sure to have `jinja` installed before using `load_or_create_model_card`."
" To install it, please run `pip install Jinja2`."
)
try:
# Check if the model card is present on the remote repo
model_card = ModelCard.load(repo_id_or_path, token=token)
except (EntryNotFoundError, RepositoryNotFoundError):
# Otherwise create a model card from template
if from_training:
model_card = ModelCard.from_template(
card_data=ModelCardData( # Card metadata object that will be converted to YAML block
license=license,
library_name="diffusers",
inference=inference,
base_model=base_model,
instance_prompt=prompt,
widget=widget,
),
template_path=MODEL_CARD_TEMPLATE_PATH,
model_description=model_description,
)
else:
card_data = ModelCardData()
component = "pipeline" if is_pipeline else "model"
if model_description is None:
model_description = f"This is the model card of a 馃Ж diffusers {component} that has been pushed on the Hub. This model card has been automatically generated."
model_card = ModelCard.from_template(card_data, model_description=model_description)
return model_card
def populate_model_card(model_card: ModelCard, tags: Union[str, List[str]] = None) -> ModelCard:
"""Populates the `model_card` with library name and optional tags."""
if model_card.data.library_name is None:
model_card.data.library_name = "diffusers"
if tags is not None:
if isinstance(tags, str):
tags = [tags]
if model_card.data.tags is None:
model_card.data.tags = []
for tag in tags:
model_card.data.tags.append(tag)
return model_card
def extract_commit_hash(resolved_file: Optional[str], commit_hash: Optional[str] = None):
"""
Extracts the commit hash from a resolved filename toward a cache file.
"""
if resolved_file is None or commit_hash is not None:
return commit_hash
resolved_file = str(Path(resolved_file).as_posix())
search = re.search(r"snapshots/([^/]+)/", resolved_file)
if search is None:
return None
commit_hash = search.groups()[0]
return commit_hash if REGEX_COMMIT_HASH.match(commit_hash) else None
def _add_variant(weights_name: str, variant: Optional[str] = None) -> str:
if variant is not None:
splits = weights_name.split(".")
splits = splits[:-1] + [variant] + splits[-1:]
weights_name = ".".join(splits)
return weights_name
@validate_hf_hub_args
def _get_model_file(
pretrained_model_name_or_path: Union[str, Path],
*,
weights_name: str,
subfolder: Optional[str] = None,
cache_dir: Optional[str] = None,
force_download: bool = False,
proxies: Optional[Dict] = None,
local_files_only: bool = False,
token: Optional[str] = None,
user_agent: Optional[Union[Dict, str]] = None,
revision: Optional[str] = None,
commit_hash: Optional[str] = None,
dduf_entries: Optional[Dict[str, DDUFEntry]] = None,
):
pretrained_model_name_or_path = str(pretrained_model_name_or_path)
if dduf_entries:
if subfolder is not None:
raise ValueError(
"DDUF file only allow for 1 level of directory (e.g transformer/model1/model.safetentors is not allowed). "
"Please check the DDUF structure"
)
model_file = (
weights_name
if pretrained_model_name_or_path == ""
else "/".join([pretrained_model_name_or_path, weights_name])
)
if model_file in dduf_entries:
return model_file
else:
raise EnvironmentError(f"Error no file named {weights_name} found in archive {dduf_entries.keys()}.")
elif os.path.isfile(pretrained_model_name_or_path):
return pretrained_model_name_or_path
elif os.path.isdir(pretrained_model_name_or_path):
if os.path.isfile(os.path.join(pretrained_model_name_or_path, weights_name)):
# Load from a PyTorch checkpoint
model_file = os.path.join(pretrained_model_name_or_path, weights_name)
return model_file
elif subfolder is not None and os.path.isfile(
os.path.join(pretrained_model_name_or_path, subfolder, weights_name)
):
model_file = os.path.join(pretrained_model_name_or_path, subfolder, weights_name)
return model_file
else:
raise EnvironmentError(
f"Error no file named {weights_name} found in directory {pretrained_model_name_or_path}."
)
else:
# 1. First check if deprecated way of loading from branches is used
if (
revision in DEPRECATED_REVISION_ARGS
and (weights_name == WEIGHTS_NAME or weights_name == SAFETENSORS_WEIGHTS_NAME)
and version.parse(version.parse(__version__).base_version) >= version.parse("0.22.0")
):
try:
model_file = hf_hub_download(
pretrained_model_name_or_path,
filename=_add_variant(weights_name, revision),
cache_dir=cache_dir,
force_download=force_download,
proxies=proxies,
local_files_only=local_files_only,
token=token,
user_agent=user_agent,
subfolder=subfolder,
revision=revision or commit_hash,
)
warnings.warn(
f"Loading the variant {revision} from {pretrained_model_name_or_path} via `revision='{revision}'` is deprecated. Loading instead from `revision='main'` with `variant={revision}`. Loading model variants via `revision='{revision}'` will be removed in diffusers v1. Please use `variant='{revision}'` instead.",
FutureWarning,
)
return model_file
except: # noqa: E722
warnings.warn(
f"You are loading the variant {revision} from {pretrained_model_name_or_path} via `revision='{revision}'`. This behavior is deprecated and will be removed in diffusers v1. One should use `variant='{revision}'` instead. However, it appears that {pretrained_model_name_or_path} currently does not have a {_add_variant(weights_name, revision)} file in the 'main' branch of {pretrained_model_name_or_path}. \n The Diffusers team and community would be very grateful if you could open an issue: https://github.com/huggingface/diffusers/issues/new with the title '{pretrained_model_name_or_path} is missing {_add_variant(weights_name, revision)}' so that the correct variant file can be added.",
FutureWarning,
)
try:
# 2. Load model file as usual
model_file = hf_hub_download(
pretrained_model_name_or_path,
filename=weights_name,
cache_dir=cache_dir,
force_download=force_download,
proxies=proxies,
local_files_only=local_files_only,
token=token,
user_agent=user_agent,
subfolder=subfolder,
revision=revision or commit_hash,
)
return model_file
except RepositoryNotFoundError as e:
raise EnvironmentError(
f"{pretrained_model_name_or_path} is not a local folder and is not a valid model identifier "
"listed on 'https://huggingface.co/models'\nIf this is a private repository, make sure to pass a "
"token having permission to this repo with `token` or log in with `huggingface-cli "
"login`."
) from e
except RevisionNotFoundError as e:
raise EnvironmentError(
f"{revision} is not a valid git identifier (branch name, tag name or commit id) that exists for "
"this model name. Check the model page at "
f"'https://huggingface.co/{pretrained_model_name_or_path}' for available revisions."
) from e
except EntryNotFoundError as e:
raise EnvironmentError(
f"{pretrained_model_name_or_path} does not appear to have a file named {weights_name}."
) from e
except HTTPError as e:
raise EnvironmentError(
f"There was a specific connection error when trying to load {pretrained_model_name_or_path}:\n{e}"
) from e
except ValueError as e:
raise EnvironmentError(
f"We couldn't connect to '{HUGGINGFACE_CO_RESOLVE_ENDPOINT}' to load this model, couldn't find it"
f" in the cached files and it looks like {pretrained_model_name_or_path} is not the path to a"
f" directory containing a file named {weights_name} or"
" \nCheckout your internet connection or see how to run the library in"
" offline mode at 'https://huggingface.co/docs/diffusers/installation#offline-mode'."
) from e
except EnvironmentError as e:
raise EnvironmentError(
f"Can't load the model for '{pretrained_model_name_or_path}'. If you were trying to load it from "
"'https://huggingface.co/models', make sure you don't have a local directory with the same name. "
f"Otherwise, make sure '{pretrained_model_name_or_path}' is the correct path to a directory "
f"containing a file named {weights_name}"
) from e
# Adapted from
# https://github.com/huggingface/transformers/blob/1360801a69c0b169e3efdbb0cd05d9a0e72bfb70/src/transformers/utils/hub.py#L976
# Differences are in parallelization of shard downloads and checking if shards are present.
def _check_if_shards_exist_locally(local_dir, subfolder, original_shard_filenames):
shards_path = os.path.join(local_dir, subfolder)
shard_filenames = [os.path.join(shards_path, f) for f in original_shard_filenames]
for shard_file in shard_filenames:
if not os.path.exists(shard_file):
raise ValueError(
f"{shards_path} does not appear to have a file named {shard_file} which is "
"required according to the checkpoint index."
)
def _get_checkpoint_shard_files(
pretrained_model_name_or_path,
index_filename,
cache_dir=None,
proxies=None,
local_files_only=False,
token=None,
user_agent=None,
revision=None,
subfolder="",
dduf_entries: Optional[Dict[str, DDUFEntry]] = None,
):
"""
For a given model:
- download and cache all the shards of a sharded checkpoint if `pretrained_model_name_or_path` is a model ID on the
Hub
- returns the list of paths to all the shards, as well as some metadata.
For the description of each arg, see [`PreTrainedModel.from_pretrained`]. `index_filename` is the full path to the
index (downloaded and cached if `pretrained_model_name_or_path` is a model ID on the Hub).
"""
if dduf_entries:
if index_filename not in dduf_entries:
raise ValueError(f"Can't find a checkpoint index ({index_filename}) in {pretrained_model_name_or_path}.")
else:
if not os.path.isfile(index_filename):
raise ValueError(f"Can't find a checkpoint index ({index_filename}) in {pretrained_model_name_or_path}.")
if dduf_entries:
index = json.loads(dduf_entries[index_filename].read_text())
else:
with open(index_filename, "r") as f:
index = json.loads(f.read())
original_shard_filenames = sorted(set(index["weight_map"].values()))
sharded_metadata = index["metadata"]
sharded_metadata["all_checkpoint_keys"] = list(index["weight_map"].keys())
sharded_metadata["weight_map"] = index["weight_map"].copy()
shards_path = os.path.join(pretrained_model_name_or_path, subfolder)
# First, let's deal with local folder.
if os.path.isdir(pretrained_model_name_or_path):
_check_if_shards_exist_locally(
pretrained_model_name_or_path, subfolder=subfolder, original_shard_filenames=original_shard_filenames
)
return shards_path, sharded_metadata
elif dduf_entries:
return shards_path, sharded_metadata
# At this stage pretrained_model_name_or_path is a model identifier on the Hub
allow_patterns = original_shard_filenames
if subfolder is not None:
allow_patterns = [os.path.join(subfolder, p) for p in allow_patterns]
ignore_patterns = ["*.json", "*.md"]
# `model_info` call must guarded with the above condition.
model_files_info = model_info(pretrained_model_name_or_path, revision=revision, token=token)
for shard_file in original_shard_filenames:
shard_file_present = any(shard_file in k.rfilename for k in model_files_info.siblings)
if not shard_file_present:
raise EnvironmentError(
f"{shards_path} does not appear to have a file named {shard_file} which is "
"required according to the checkpoint index."
)
try:
# Load from URL
cached_folder = snapshot_download(
pretrained_model_name_or_path,
cache_dir=cache_dir,
proxies=proxies,
local_files_only=local_files_only,
token=token,
revision=revision,
allow_patterns=allow_patterns,
ignore_patterns=ignore_patterns,
user_agent=user_agent,
)
if subfolder is not None:
cached_folder = os.path.join(cached_folder, subfolder)
# We have already dealt with RepositoryNotFoundError and RevisionNotFoundError when getting the index, so
# we don't have to catch them here. We have also dealt with EntryNotFoundError.
except HTTPError as e:
raise EnvironmentError(
f"We couldn't connect to '{HUGGINGFACE_CO_RESOLVE_ENDPOINT}' to load {pretrained_model_name_or_path}. You should try"
" again after checking your internet connection."
) from e
return cached_folder, sharded_metadata
def _check_legacy_sharding_variant_format(folder: str = None, filenames: List[str] = None, variant: str = None):
if filenames and folder:
raise ValueError("Both `filenames` and `folder` cannot be provided.")
if not filenames:
filenames = []
for _, _, files in os.walk(folder):
for file in files:
filenames.append(os.path.basename(file))
transformers_index_format = r"\d{5}-of-\d{5}"
variant_file_re = re.compile(rf".*-{transformers_index_format}\.{variant}\.[a-z]+$")
return any(variant_file_re.match(f) is not None for f in filenames)
class PushToHubMixin:
"""
A Mixin to push a model, scheduler, or pipeline to the Hugging Face Hub.
"""
def _upload_folder(
self,
working_dir: Union[str, os.PathLike],
repo_id: str,
token: Optional[str] = None,
commit_message: Optional[str] = None,
create_pr: bool = False,
):
"""
Uploads all files in `working_dir` to `repo_id`.
"""
if commit_message is None:
if "Model" in self.__class__.__name__:
commit_message = "Upload model"
elif "Scheduler" in self.__class__.__name__:
commit_message = "Upload scheduler"
else:
commit_message = f"Upload {self.__class__.__name__}"
logger.info(f"Uploading the files of {working_dir} to {repo_id}.")
return upload_folder(
repo_id=repo_id, folder_path=working_dir, token=token, commit_message=commit_message, create_pr=create_pr
)
def push_to_hub(
self,
repo_id: str,
commit_message: Optional[str] = None,
private: Optional[bool] = None,
token: Optional[str] = None,
create_pr: bool = False,
safe_serialization: bool = True,
variant: Optional[str] = None,
) -> str:
"""
Upload model, scheduler, or pipeline files to the 馃 Hugging Face Hub.
Parameters:
repo_id (`str`):
The name of the repository you want to push your model, scheduler, or pipeline files to. It should
contain your organization name when pushing to an organization. `repo_id` can also be a path to a local
directory.
commit_message (`str`, *optional*):
Message to commit while pushing. Default to `"Upload {object}"`.
private (`bool`, *optional*):
Whether to make the repo private. If `None` (default), the repo will be public unless the
organization's default is private. This value is ignored if the repo already exists.
token (`str`, *optional*):
The token to use as HTTP bearer authorization for remote files. The token generated when running
`huggingface-cli login` (stored in `~/.huggingface`).
create_pr (`bool`, *optional*, defaults to `False`):
Whether or not to create a PR with the uploaded files or directly commit.
safe_serialization (`bool`, *optional*, defaults to `True`):
Whether or not to convert the model weights to the `safetensors` format.
variant (`str`, *optional*):
If specified, weights are saved in the format `pytorch_model.<variant>.bin`.
Examples:
```python
from diffusers import UNet2DConditionModel
unet = UNet2DConditionModel.from_pretrained("stabilityai/stable-diffusion-2", subfolder="unet")
# Push the `unet` to your namespace with the name "my-finetuned-unet".
unet.push_to_hub("my-finetuned-unet")
# Push the `unet` to an organization with the name "my-finetuned-unet".
unet.push_to_hub("your-org/my-finetuned-unet")
```
"""
repo_id = create_repo(repo_id, private=private, token=token, exist_ok=True).repo_id
# Create a new empty model card and eventually tag it
model_card = load_or_create_model_card(repo_id, token=token)
model_card = populate_model_card(model_card)
# Save all files.
save_kwargs = {"safe_serialization": safe_serialization}
if "Scheduler" not in self.__class__.__name__:
save_kwargs.update({"variant": variant})
with tempfile.TemporaryDirectory() as tmpdir:
self.save_pretrained(tmpdir, **save_kwargs)
# Update model card if needed:
model_card.save(os.path.join(tmpdir, "README.md"))
return self._upload_folder(
tmpdir,
repo_id,
token=token,
commit_message=commit_message,
create_pr=create_pr,
)